Hugging Face's logo

mlfoundations-dev
/
stackoverflow_10000tasks_1p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
11e4e9b
•
1 Parent(s): 7a2cd70

Training in progress, epoch 3

Browse files
Files changed (5) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe578fc498ab1479a12bfa06c1e3330b63a2b7e3740e705549096d9f270ff713
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04ad86bac86c815b02e3340b60d21c4e1a9e7338be6667638b896a6e799cb0e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2c31779e14fbaf60191f3bea3d66eeaf7738f32a866f729e4ecf127530cc87b
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfcb780206b27787ce44c9b4d3fa1f5c3b52769f34b75cece95bfdd500f8a0b
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfbae3ad23625a94fc39d9bed5c798b28e11811b70293ed5bf683cb7c6586dcc
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c076a6e97d35bb7b0600501e5b541845e35b1d08494baad7488f6f705d0d1c8
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15f1091181b4fcb5a368ad2d48df8b3152280d008c92376b25ed44982c50851f
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9002f02e4436823a6bc0e34745bfc81b1e7170ff32ff7e3775ff3130ae224abc
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -7,3 +7,8 @@
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7735, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:47", "remaining_time": "0:25:20"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7691, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:08", "remaining_time": "0:19:34"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.7998312711715698, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:32", "remaining_time": "0:19:46"}
 
 
 
 
 
 
7
  {"current_steps": 60, "total_steps": 105, "loss": 0.7735, "lr": 5e-06, "epoch": 1.7142857142857144, "percentage": 57.14, "elapsed_time": "0:33:47", "remaining_time": "0:25:20"}
8
  {"current_steps": 70, "total_steps": 105, "loss": 0.7691, "lr": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:08", "remaining_time": "0:19:34"}
9
  {"current_steps": 70, "total_steps": 105, "eval_loss": 0.7998312711715698, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:39:32", "remaining_time": "0:19:46"}
10
+ {"current_steps": 80, "total_steps": 105, "loss": 0.7154, "lr": 5e-06, "epoch": 2.2857142857142856, "percentage": 76.19, "elapsed_time": "0:46:10", "remaining_time": "0:14:25"}
11
+ {"current_steps": 90, "total_steps": 105, "loss": 0.7088, "lr": 5e-06, "epoch": 2.571428571428571, "percentage": 85.71, "elapsed_time": "0:51:31", "remaining_time": "0:08:35"}
12
+ {"current_steps": 100, "total_steps": 105, "loss": 0.7039, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "0:56:51", "remaining_time": "0:02:50"}
13
+ {"current_steps": 105, "total_steps": 105, "eval_loss": 0.7979986071586609, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:01:15", "remaining_time": "0:00:00"}
14
+ {"current_steps": 105, "total_steps": 105, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:02:31", "remaining_time": "0:00:00"}